© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2306
    Prev
    Next
    INDEX
    Explanations

    Node.js and compiler

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    2.90
    2.72
    :
    2.16
    /
    2.10
     &
    2.09
     The
    2.03
    ,
    1.96
     О
    1.96
     N
    1.96
     -
    1.94
    POSITIVE LOGITS
     kehnd
    2.83
     benöt
    2.78
    <unused1498>
    2.76
    𒈣
    2.76
    𒊨
    2.75
     ivvu
    2.75
    𒀌
    2.74
    <unused1305>
    2.73
     क़ुर्आन
    2.72
    <unused67>
    2.72
    Activations Density 0.006%

    No Known Activations